self-bench

Builds Harbor-formatted, private coding-agent benchmarks from your own GitHub repositories.

PlatformWebfreeglobal

self-bench builds Harbor-formatted, private coding-agent benchmarks from a team's own GitHub repositories, letting them evaluate how well a coding agent performs on their actual codebase instead of relying only on generic public benchmarks.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of self-bench - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim self-bench to unlock →

Something wrong with this listing — dead link, not a real product, wrong info?

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether self-bench (or something else) actually fits.

Try a problem